mHuBERT-147-br / vocab.json
gweltou's picture
Upload tokenizer
a7b790b verified
raw
history blame
No virus
635 Bytes
{
"'": 53,
"3": 24,
"A": 13,
"E": 6,
"I": 31,
"O": 0,
"S": 34,
"X": 37,
"Z": 14,
"[PAD]": 55,
"[UNK]": 54,
"a": 30,
"b": 28,
"c": 32,
"d": 27,
"e": 19,
"f": 52,
"g": 1,
"h": 39,
"i": 36,
"j": 18,
"k": 43,
"l": 44,
"m": 38,
"n": 20,
"o": 33,
"p": 3,
"q": 16,
"r": 9,
"s": 10,
"t": 5,
"u": 41,
"v": 21,
"w": 49,
"x": 46,
"y": 17,
"z": 22,
"|": 35,
"Ù": 42,
"à": 48,
"á": 8,
"â": 15,
"ã": 45,
"ç": 2,
"è": 51,
"é": 29,
"ê": 4,
"ë": 7,
"ñ": 12,
"ô": 47,
"ö": 23,
"ø": 50,
"ù": 25,
"û": 40,
"ü": 11,
"ı": 26
}